{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:EGAC5MEJPCXPZIAEPYEIUWDTMR","short_pith_number":"pith:EGAC5MEJ","canonical_record":{"source":{"id":"2403.11299","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-17T18:42:38Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"title_canon_sha256":"45949ca479d5c42fbf965ba6d9f296f4990f3ef0c77a5a58adec03354143eab4","abstract_canon_sha256":"2dff4e4bfe4e15eda7ed2f1afaef8a865ed265a665b66604a1ce448e165d2fdc"},"schema_version":"1.0"},"canonical_sha256":"21802eb08978aefca0047e088a587364627e4dd40890e8da407bcf6e28a67a42","source":{"kind":"arxiv","id":"2403.11299","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.11299","created_at":"2026-07-05T08:43:54Z"},{"alias_kind":"arxiv_version","alias_value":"2403.11299v2","created_at":"2026-07-05T08:43:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.11299","created_at":"2026-07-05T08:43:54Z"},{"alias_kind":"pith_short_12","alias_value":"EGAC5MEJPCXP","created_at":"2026-07-05T08:43:54Z"},{"alias_kind":"pith_short_16","alias_value":"EGAC5MEJPCXPZIAE","created_at":"2026-07-05T08:43:54Z"},{"alias_kind":"pith_short_8","alias_value":"EGAC5MEJ","created_at":"2026-07-05T08:43:54Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:EGAC5MEJPCXPZIAEPYEIUWDTMR","target":"record","payload":{"canonical_record":{"source":{"id":"2403.11299","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-17T18:42:38Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"title_canon_sha256":"45949ca479d5c42fbf965ba6d9f296f4990f3ef0c77a5a58adec03354143eab4","abstract_canon_sha256":"2dff4e4bfe4e15eda7ed2f1afaef8a865ed265a665b66604a1ce448e165d2fdc"},"schema_version":"1.0"},"canonical_sha256":"21802eb08978aefca0047e088a587364627e4dd40890e8da407bcf6e28a67a42","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:43:54.017450Z","signature_b64":"4NxKBUjb45ujrmUdK4446ooiwPk3X4/WCn4Uay+wumu8xZCM61c20xq/wGkV56kCJVeZHWoddwU2WZmE42F6CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"21802eb08978aefca0047e088a587364627e4dd40890e8da407bcf6e28a67a42","last_reissued_at":"2026-07-05T08:43:54.016954Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:43:54.016954Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2403.11299","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:43:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6SD9j9CbbJcghtHlU6RpPXBSIZ5l4kRlw2yRey4oWAb6pLYVJpucfvdDqjnyP6N+qrWDJW41WFq7Q1mNhi5rCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T14:17:24.382296Z"},"content_sha256":"872fc43a78b7d1d2e583f3d12d96ae4b9fc2acdad88e32023cb65f70082e2884","schema_version":"1.0","event_id":"sha256:872fc43a78b7d1d2e583f3d12d96ae4b9fc2acdad88e32023cb65f70082e2884"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:EGAC5MEJPCXPZIAEPYEIUWDTMR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SQ-LLaVA: Self-Questioning for Large Vision-Language Assistant","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Can Qin, Guohao Sun, Jiamian Wang, Ran Xu, Zeyuan Chen, Zhiqiang Tao","submitted_at":"2024-03-17T18:42:38Z","abstract_excerpt":"Recent advances in vision-language models have shown notable generalization in broad tasks through visual instruction tuning. However, bridging the gap between the pre-trained vision encoder and the large language models (LLMs) becomes the whole network's bottleneck. To improve cross-modality alignment, existing works usually consider more visual instruction data covering a broader range of vision tasks to fine-tune the model for question-answering, which, however, is costly to obtain and has not thoroughly explored the rich contextual information contained in images. This paper first attempts"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.11299","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2403.11299/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:43:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Xog91WD/tqDk5ny6E9bKzoxNYIbvbJQB95jZwC/9mb80FgTPS885A7Fu+PMeM3JYweBKF3I75CNFSwLn3POoCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T14:17:24.383200Z"},"content_sha256":"4e4f1afe3c0b311826f10e43ada9f6c908fdb05a40fa2476d76ffe6fd31ed907","schema_version":"1.0","event_id":"sha256:4e4f1afe3c0b311826f10e43ada9f6c908fdb05a40fa2476d76ffe6fd31ed907"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EGAC5MEJPCXPZIAEPYEIUWDTMR/bundle.json","state_url":"https://pith.science/pith/EGAC5MEJPCXPZIAEPYEIUWDTMR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EGAC5MEJPCXPZIAEPYEIUWDTMR/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-18T14:17:24Z","links":{"resolver":"https://pith.science/pith/EGAC5MEJPCXPZIAEPYEIUWDTMR","bundle":"https://pith.science/pith/EGAC5MEJPCXPZIAEPYEIUWDTMR/bundle.json","state":"https://pith.science/pith/EGAC5MEJPCXPZIAEPYEIUWDTMR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EGAC5MEJPCXPZIAEPYEIUWDTMR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:EGAC5MEJPCXPZIAEPYEIUWDTMR","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"2dff4e4bfe4e15eda7ed2f1afaef8a865ed265a665b66604a1ce448e165d2fdc","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-17T18:42:38Z","title_canon_sha256":"45949ca479d5c42fbf965ba6d9f296f4990f3ef0c77a5a58adec03354143eab4"},"schema_version":"1.0","source":{"id":"2403.11299","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.11299","created_at":"2026-07-05T08:43:54Z"},{"alias_kind":"arxiv_version","alias_value":"2403.11299v2","created_at":"2026-07-05T08:43:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.11299","created_at":"2026-07-05T08:43:54Z"},{"alias_kind":"pith_short_12","alias_value":"EGAC5MEJPCXP","created_at":"2026-07-05T08:43:54Z"},{"alias_kind":"pith_short_16","alias_value":"EGAC5MEJPCXPZIAE","created_at":"2026-07-05T08:43:54Z"},{"alias_kind":"pith_short_8","alias_value":"EGAC5MEJ","created_at":"2026-07-05T08:43:54Z"}],"graph_snapshots":[{"event_id":"sha256:4e4f1afe3c0b311826f10e43ada9f6c908fdb05a40fa2476d76ffe6fd31ed907","target":"graph","created_at":"2026-07-05T08:43:54Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2403.11299/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advances in vision-language models have shown notable generalization in broad tasks through visual instruction tuning. However, bridging the gap between the pre-trained vision encoder and the large language models (LLMs) becomes the whole network's bottleneck. To improve cross-modality alignment, existing works usually consider more visual instruction data covering a broader range of vision tasks to fine-tune the model for question-answering, which, however, is costly to obtain and has not thoroughly explored the rich contextual information contained in images. This paper first attempts","authors_text":"Can Qin, Guohao Sun, Jiamian Wang, Ran Xu, Zeyuan Chen, Zhiqiang Tao","cross_cats":["cs.AI","cs.CL","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-17T18:42:38Z","title":"SQ-LLaVA: Self-Questioning for Large Vision-Language Assistant"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.11299","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:872fc43a78b7d1d2e583f3d12d96ae4b9fc2acdad88e32023cb65f70082e2884","target":"record","created_at":"2026-07-05T08:43:54Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"2dff4e4bfe4e15eda7ed2f1afaef8a865ed265a665b66604a1ce448e165d2fdc","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-17T18:42:38Z","title_canon_sha256":"45949ca479d5c42fbf965ba6d9f296f4990f3ef0c77a5a58adec03354143eab4"},"schema_version":"1.0","source":{"id":"2403.11299","kind":"arxiv","version":2}},"canonical_sha256":"21802eb08978aefca0047e088a587364627e4dd40890e8da407bcf6e28a67a42","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"21802eb08978aefca0047e088a587364627e4dd40890e8da407bcf6e28a67a42","first_computed_at":"2026-07-05T08:43:54.016954Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:43:54.016954Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4NxKBUjb45ujrmUdK4446ooiwPk3X4/WCn4Uay+wumu8xZCM61c20xq/wGkV56kCJVeZHWoddwU2WZmE42F6CA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:43:54.017450Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.11299","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:872fc43a78b7d1d2e583f3d12d96ae4b9fc2acdad88e32023cb65f70082e2884","sha256:4e4f1afe3c0b311826f10e43ada9f6c908fdb05a40fa2476d76ffe6fd31ed907"],"state_sha256":"6398aee7293962b8e1d17a3b627a6c4d06d73399d327ceeb99a3cd07f1ecf552"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FI7za9QTrUaMRTBQqSYL/0m271dIFADy7Jk2fBC+ACibMC/Sigmg0xQmN0yA3MlNRR38SCso6VkXkC5p4ALXBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T14:17:24.391052Z","bundle_sha256":"eb38013b04c8227704dce85320d80aa62bee326dd336325d3c8080a9963a72a9"}}